Download pdf - Kolmogorov-Sminov Test

Kolmogorov-Sminov Test

• The Kolmogorov-Smirnov test (also known as the K-S test or one-sample Kolmogorov-Smirnov test) is a nonparametric procedure that determines whether a sample of data comes from a specific distribution, i.e., normal, uniform, Poisson, or exponential distribution.

• It is mostly used for evaluating the assumption of univariate normality by taking the observed cumulative distribution of scores and comparing them to the theoretical cumulative distribution for a normally distributed variable.

Kolmogorov-Sminov Test • Three set of data we

have.

• We wanted to check the distribution type for each set of data


• Follow the menu as indicated to conduct the K-S test using Legacy Dialogs.


• Our hypothesis is like;

• 𝐻0 =𝐷𝑖𝑠𝑡𝑟𝑖𝑏𝑢𝑡𝑖𝑜𝑛 𝑜𝑓 𝐷𝑎𝑡𝑎 𝑖𝑠 𝑁𝑜𝑟𝑚𝑎𝑙

• 𝐻1 =𝐷𝑖𝑠𝑡𝑟𝑖𝑏𝑢𝑡𝑖𝑜𝑛 𝑜𝑓 𝐷𝑎𝑡𝑎 𝑖𝑠 𝑛𝑜𝑡 𝑁𝑜𝑟𝑚𝑎𝑙

• So if our significant value is greater (>) than alpha (0,05), we failed to reject 𝐻0 if our significant value is less (<) than alpha (0,05), we reject 𝐻0


• As we all see our significant value is 0,292 which far more greater than 0,05. So, we fail to reject 𝐻0. That means, our data “Normally Distributed”

What is linear regression ?

linear regression is a linear approach to modelling the relationship between a scalar response (or dependent variable y ) and one or more explanatory variables (or independent variables x).

X

Y

Example :

In this set of data, we wanted to

predict a person IQ scores if we

know how much caffeine they

consume.

Our set of Data is as follows :

Caffeine Dose IQ Score 50 100

60 102

80 107

90 105

110 112

150 108

150 103

160 109

180 109

200 112

200 120

210 114

210 118

220 121

220 120

250 130

260 127

260 131

280 132

300 135

Step 1 : input our data

Write the variables

And the data :

Step 2 : Plot the Data

In this step , we are going to plot our data in order so see the

shape of the graph y = f(x)

What are y and x ??

Remember that in our example we wanted to know the effect

of the consumption of caffeine on the IQ Score (Intelligence

quotient).

Otherwise , we want to know if the IQ score depends on the

caffeine dose.

So y is IQ score

And x is caffeine dose

In order to plot the data ,we use the graphs tool :

1- Go “Graph” then “Legacy Dialogs” and choose “Scatter Dot”

2- Then choose “Simple Scatter” and click “Define

3- So remember

variable you’re trying

to predict is y variable,

we should put

“IQ_scores” in y axis

and, and the variable

that you are using to

predict y variable is

the x variable which is

“Caffeine dose” in this

case

We obtain :

So as you can see on the

graph relationship is almost

like a straight line. So, linear

regression will be most

appropriate one for this

example.

Step 3 : find de function y

In this step we will find the regression equation

𝑦 = 𝑏𝑥 + 𝑎 Where :

Y = value of variable being predicted (IQ score in this case)

b = slope of a line

x = value of variable you already know

a = y intercept.

1-Go “Analyze” then

“Regression” So there are

many different kind of

relationship style between

two variables it could be

linear, or bell shaped or any

other kind.

pick “Linear”

2- pick your

“Caffein_Dose” as

independent variable

because you are using it

to predict, and

“IQ_score” will be your

dependent variable

because you’re looking

for its value.

We obtain:

Under standardized

Coefficients at B

section first one 91.308

is you’re “a” means it’s

your y intercept and the

second value .134 is

your “b” means slope so

if you put this numbers

in your y=bx+a you can

predict a person’s IQ

score according to how

much caffeine which

he/she consumed.

For example , how much will be the IQ score of a person who

consumed 70 dose of caffeine ?

Answer :

We know that y = bx+a

=0,134 x + 91.308

y = 0,13 * 70 + 91,308

= 100,408